A New Color Manipulation Method and Dehazing for Enhancement of Underwater Images
M. Kanagavel, V Thanikaiselvan · 2025
In this article, a new underwater image enhancement method is proposed based on image classification and blending of color manipulation and dehazing. First, the underwater images are classified majorly into three types: water haze image, blue toned image and green toned image, using the mean pixel intensity of color channels in RGB space. Further, depending upon the maximum pixel intensity level of blue and green channels, the blue toned and green toned images are classified into two subtypes: blue-green and green-blue toned images. The water haze images are enhanced using the shades of grey method followed by dehazing by Dark Channel Prior (DCP). The green and blue toned images are enhanced by color mixing method followed by DCP. The blue-green and green-blue images are improved by a new proposed color manipulation method followed by DCP. The experimental results show that the proposed approach outperforms the state-of-the-art qualitatively and quantitatively in terms of Underwater Image Quality Metrics (UIQM).